← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
1k
tokens
448.0
PP tok/s
49.3
TG tok/s
2286
TTFT (ms)
20.0
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 448.0 | 49.3 | 20.0 GB | current |
| 4k | 459.8 | 46.7 | 20.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 49.3 | 1.00× |
| 2× | 75.5 | 1.53× |
| 4× | 88.7 | 1.80× |